install.packages("tidyverse")
install.packages("hrbrthemes")
install.packages("viridis")

 
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)

## 5 HISTOGRAMA
#Histograma
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/1_OneNum.csv", header=TRUE)

# Make the histogram
data %>%
  filter( price<300 ) %>%
  ggplot( aes(x=price)) +
  stat_bin(breaks=seq(0,300,10), fill="#69b3a2", color="#e9ecef", alpha=0.9) +
  ggtitle("Night price distribution of Airbnb appartements")# +
  #theme_ipsum()


##6 GRÁFICO DE DENSIDAD
#Histograma utilizando density
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)

# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/1_OneNum.csv", header=TRUE)

# Make the histogram
data %>%
  filter( price<300 ) %>%
  ggplot( aes(x=price)) +
  geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.8) +
  ggtitle("Night price distribution of Airbnb appartements")# +
#  theme_ipsum()

#Utilizar density para dos variables de forma inteligente (violín?)
data <- data.frame(
  x = rnorm(1000), 
  y = rnorm(1000, mean=2)
)
data %>% 
  ggplot( aes(x) ) + 
  stat_bin( aes(x = x, y = ..density..), binwidth = diff(range(data$x))/30, fill="#69b3a2" ) + 
  geom_label( aes(x=4.5, y=0.25, label="variable1"), color="#69b3a2") +
  geom_density( aes(x = y, y = -..density..), binwidth = diff(range(data$x))/30, fill= "#404080") +
  geom_label( aes(x=4.5, y=-0.25, label="variable2"), color="#404080") +
  theme_ipsum() +
  xlab("value of x")

##7 GRÁFICO DE DISPERSIÓN
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/2_TwoNum.csv", header=T, sep=",") %>% dplyr::select(GrLivArea, SalePrice)
# plot
data %>% 
  ggplot( aes(x=GrLivArea, y=SalePrice/1000)) +
  geom_point(color="#69b3a2", alpha=0.8) +
  ggtitle("Ground living area partially explains sale price of apartments") +
  theme_ipsum() +
  theme(
    plot.title = element_text(size=12)
  ) +
  ylab('Sale price (k$)') +
  xlab('Ground living area')

library(ggExtra)
# create a ggplot2 scatterplot
p <- data %>%
  ggplot( aes(x=GrLivArea, y=SalePrice/1000)) +
  geom_point(color="#69b3a2", alpha=0.8) +
  theme_ipsum() +
  theme(
    legend.position="none"
  )
# add marginal histograms
ggExtra::ggMarginal(p, type = "histogram", color="grey")

##8 GRÁFICO DE DENSIDAD
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)
library(patchwork)
# Dataset:
a <- data.frame( x=rnorm(20000, 10, 1.2), y=rnorm(20000, 10, 1.2), group=rep("A",20000))
b <- data.frame( x=rnorm(20000, 14.5, 1.2), y=rnorm(20000, 14.5, 1.2), group=rep("B",20000))
c <- data.frame( x=rnorm(20000, 9.5, 1.5), y=rnorm(20000, 15.5, 1.5), group=rep("C",20000))
data <- do.call(rbind, list(a,b,c))               
p1 <- data %>%
  ggplot( aes(x=x, y=y)) +
  geom_point(color="#69b3a2", size=2) +
  theme_ipsum() +
  theme(
    legend.position="none"
  )
p2 <- ggplot(data, aes(x=x, y=y) ) +
  stat_density_2d(aes(fill = ..density..), geom = "raster", contour = FALSE) +
  scale_x_continuous(expand = c(0, 0)) +
  scale_y_continuous(expand = c(0, 0)) +
  scale_fill_viridis() +
  theme(
    legend.position='none'
  )
p1 + p2

##9 DISTRIBUCIÓN MARGINAL
# library
library(ggplot2)
library(ggExtra)
# The mtcars dataset is proposed in R
head(mtcars)
# classic plot :
p <- ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, size=cyl)) +
  geom_point() +
  theme(legend.position="none")
# with marginal histogram
p1 <- ggMarginal(p, type="histogram")
# marginal density
p1
p2 <- ggMarginal(p, type="density")
# marginal boxplot
p2
p3 <- ggMarginal(p, type="boxplot")
p3

##10 PLOT DE LÍNEA
# Libraries
library(tidyverse)
library(hrbrthemes)
library(plotly)
library(patchwork)
library(babynames)
library(viridis)
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/3_TwoNumOrdered.csv", header=T)
data$date <- as.Date(data$date)
# plot
data %>%
  ggplot( aes(x=date, y=value)) +
  geom_line(color="#69b3a2") +
  ggtitle("Evolution of Bitcoin price") +
  ylab("bitcoin price ($)") +
  theme_ipsum()

ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  geom_smooth(color="#69b3a2",span = 1) +
  theme_ipsum()

##11 CORRELOGRAMA
# Quick display of two cabapilities of GGally, to assess the distribution and correlation of variables 
install.packages("GGally")
library(GGally)
# Create data 
data <- data.frame( var1 = 1:100 + rnorm(100,sd=20), v2 = 1:100 + rnorm(100,sd=27), v3 = rep(1, 100) + rnorm(100, sd = 1)) 
data$v4 = data$var1 ** 2 
data$v5 = -(data$var1 ** 2) 
# Check correlations (as scatterplots), distribution and print corrleation coefficient 
ggpairs(data, title="correlogram with ggpairs()") 
# Quick display of two capabilities of GGally, to assess the distribution and correlation of variables 
library(GGally)
library(Rcpp)  
# From the help page:
data(flea)
#ggpairs(flea, columns = 2:4)  #Ojo, debería ser la línea siguiente, pero se cuelga si la ejecuto
ggpairs(flea, columns = 2:4,ggplot2::aes(colour=species))


##13 GRÁFICO DE BARRAS
# Libraries
library(tidyverse)
library(hrbrthemes)
library(kableExtra)
options(knitr.table.format = "html")
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/7_OneCatOneNum.csv", header=TRUE, sep=",")
# Barplot
data %>%
  filter(!is.na(Value)) %>%
  arrange(Value) %>%
  tail(20) %>%
  mutate(Country=factor(Country, Country)) %>%
  ggplot( aes(x=Country, y=Value) ) +
  geom_bar(stat="identity", fill="#69b3a2") +
  coord_flip() +
  theme_ipsum() +
  theme(
    panel.grid.minor.y = element_blank(),
    panel.grid.major.y = element_blank(),
    legend.position="none"
  ) +
  xlab("") +
  ylab("Weapon quantity (SIPRI trend-indicator value)")

#Gráfico de barras CIRCULAR
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/7_OneCatOneNum.csv", header=TRUE, sep=",")
# Order data
tmp <- data %>%
  filter(!is.na(Value)) %>%
  arrange(desc(Value)) %>%
  mutate(Country=factor(Country, Country))
# Set a number of 'empty bar'
empty_bar=10
# Add lines to the initial tmpset
to_add = matrix(NA, empty_bar, ncol(tmp))
colnames(to_add) = colnames(tmp)
tmp=rbind(tmp, to_add)
tmp$id=seq(1, nrow(tmp))
# Get the name and the y position of each label
label_tmp=tmp
number_of_bar=nrow(label_tmp)
angle= 90 - 360 * (label_tmp$id-0.5) /number_of_bar     # I substract 0.5 because the letter must have the angle of the center of the bars. Not extreme right(1) or extreme left (0)
label_tmp$hjust<-ifelse( angle < -90, 1, 0)
label_tmp$angle<-ifelse(angle < -90, angle+180, angle)
label_tmp$Country <- gsub("United States", "US", label_tmp$Country)
label_tmp$Country <- paste(label_tmp$Country, " (", label_tmp$Value,")", sep="")
# Make the plot
ggplot(tmp, aes(x=as.factor(id), y=Value)) +       # Note that id is a factor. If x is numeric, there is some space between the first bar
  geom_bar(stat="identity", fill=alpha("#69b3a2", 0.8)) +
  ylim(-7000,13000) +
  theme_minimal() +
  theme(
    axis.text = element_blank(),
    axis.title = element_blank(),
    panel.grid = element_blank(),
    plot.margin = unit(rep(-1,4), "cm") 
  ) +
  coord_polar(start = 0) + 
  geom_text(data=label_tmp, aes(x=id, y=Value+200, label=Country ), color="black", fontface="bold",alpha=0.6, size=2.5, angle= label_tmp$angle, hjust=label_tmp$hjust, inherit.aes = FALSE ) +
  geom_text( aes(x=24, y=8000, label="Who sells more weapons?"), color="black", inherit.aes = FALSE)


##14 BOX PLOT
# create a dataset
data <- data.frame(
  name=c( rep("A",500), rep("B",500), rep("B",500), rep("C",20), rep('D', 100)  ),
  value=c( rnorm(500, 10, 5), rnorm(500, 13, 1), rnorm(500, 18, 1), rnorm(20, 25, 4), rnorm(100, 12, 1) )
)
# sample size
sample_size = data %>% group_by(name) %>% summarize(num=n())
#Tabla usada en los plots
TablaFinal <- data %>% left_join(sample_size) %>% mutate(myaxis = paste0(name, "\n", "n=", num))
# geom_boxplot
ggplot(TablaFinal, aes(x=myaxis, y=value, fill=name)) +
  geom_boxplot()
# geom_boxplot con arreglos estáticos importantes  
ggplot(TablaFinal, aes(x=myaxis, y=value, fill=name)) +
  geom_boxplot() + 
  scale_fill_viridis(discrete = TRUE) +
  theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)) +
  ggtitle("A Boxplot") +
  xlab("")
# geom_boxplot + geom_jitter   
ggplot(TablaFinal, aes(x=myaxis, y=value, fill=name)) +
  geom_boxplot() + 
  scale_fill_viridis(discrete = TRUE) +
  geom_jitter(color="grey", size=0.7, alpha=0.5) +
  theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)) +
  ggtitle("A Boxplot") +
  xlab("")

##15  VIOLIN PLOT
# geom_violin con arreglos estáticos
ggplot(TablaFinal, aes(x=myaxis, y=value, fill=name)) +
  geom_violin(width=1.4) +
  scale_fill_viridis(discrete = TRUE) +
  theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)
  ) +
  ggtitle("Violin") +
  xlab("")
# geom_violin + geom_jitter 
ggplot(TablaFinal, aes(x=myaxis, y=value, fill=name)) +
  geom_violin(width=1.5) +
  scale_fill_viridis(discrete = TRUE) +
  geom_jitter(color="grey", size=0.7, alpha=0.5) +
  theme_ipsum() +
  theme(
    legend.position="none",
    plot.title = element_text(size=11)
  ) +
  ggtitle("Violin + geom_jitter") +
  xlab("")

##16 RIDGELINE PLOT (Gráfico de Cresta)
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)
# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/zonination/perceptions/master/probly.csv", header=TRUE, sep=",")
data <- data %>% 
  gather(key="text", value="value") %>%
  mutate(text = gsub("\\.", " ",text)) %>%
  mutate(value = round(as.numeric(value),0)) %>%
  filter(text %in% c("Almost Certainly","Very Good Chance","We Believe","Likely","About Even", "Little Chance", "Chances Are Slight", "Almost No Chance"))
install.packages("ggridges")
library(ggridges)
data %>%
  mutate(text = fct_reorder(text, value)) %>%
  ggplot( aes(y=text, x=value,  fill=text)) +
  geom_density_ridges(alpha=0.6, bandwidth=4) +
  scale_fill_viridis(discrete=TRUE) +
  scale_color_viridis(discrete=TRUE) +
  theme_ipsum() +
  theme(
    legend.position="none",
    panel.spacing = unit(0.1, "lines"),
    strip.text.x = element_text(size = 8)
  ) +
  xlab("") +
  ylab("Assigned Probability (%)")
#Dibujado del Ridgeline plot con histogramas
data %>%
  mutate(text = fct_reorder(text, value)) %>%
  ggplot( aes(y=text, x=value,  fill=text)) +
  geom_density_ridges(alpha=0.6, stat="binline", bins=20) +
  scale_fill_viridis(discrete=TRUE) +
  scale_color_viridis(discrete=TRUE) +
  theme_ipsum() +
  theme(
    legend.position="none",
    panel.spacing = unit(0.1, "lines"),
    strip.text.x = element_text(size = 8)
  ) +
  xlab("") +
  ylab("Assigned Probability (%)")



##17 WORD CLOUD
# Libraries
library(tidyverse)
library(hrbrthemes)
library(tm)
library(proustr)

# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/14_SeveralIndepLists.csv", header=TRUE) 
to_remove <- c("_|[0-9]|\\.|function|^id|script|var|div|null|typeof|opts|if|^r$|undefined|false|loaded|true|settimeout|eval|else|artist")
data <- data %>% filter(!grepl(to_remove, word)) %>% filter(!word %in% stopwords('fr')) %>% filter(!word %in% proust_stopwords()$word)

# The wordcloud 2 library is the best option for wordcloud in R
install.packages('wordcloud2')
library(wordcloud2)
# prepare a list of word (50 most frequent)
mywords <- data %>%
  filter(artist=="nekfeu") %>%
  dplyr::select(word) %>%
  group_by(word) %>%
  summarize(freq=n()) %>%
  arrange(freq) %>%
  tail(30)
# Make the plot
wordcloud2(mywords,  minRotation = -pi/2, maxRotation = -pi/2,
           backgroundColor = "white", color="#69b3a2")



##18 PIE CHART
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)
library(patchwork)
# create 3 data frame:
data1 <- data.frame( name=letters[1:5], value=c(17,18,20,22,24) )
data2 <- data.frame( name=letters[1:5], value=c(20,18,21,20,20) )
data3 <- data.frame( name=letters[1:5], value=c(24,23,21,19,18) )
# Plot
plot_pie <- function(data, vec){
  ggplot(data, aes(x="name", y=value, fill=name)) +
    geom_bar(width = 1, stat = "identity") +
    coord_polar("y", start=0, direction = -1) +
    scale_fill_viridis(discrete = TRUE,  direction=-1) + 
    geom_text(aes(y = vec, label = rev(name), size=4, color=c( "white", rep("black", 4)))) +
    scale_color_manual(values=c("black", "white")) +
    theme_ipsum() +
    theme(
      legend.position="none",
      plot.title = element_text(size=14),
      panel.grid = element_blank(),
      axis.text = element_blank(),
      legend.margin=unit(0, "null")
    ) +
    xlab("") +
    ylab("")
}
a <- plot_pie(data1, c(10,35,55,75,93))
b <- plot_pie(data2, c(10,35,53,75,93))
c <- plot_pie(data3, c(10,29,50,75,93))
a + b + c


##19 MAPA DE CALOR
install.packages('heatmaply')
library(tidyverse)
library(hrbrthemes)
library(viridis)
library(plotly)
#library(d3heatmap)

# Load data 
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/multivariate.csv", header=T, sep=";")
colnames(data) <- gsub("\\.", " ", colnames(data))

# Select a few country
data <- data %>% 
  filter(Country %in% c("France", "Sweden", "Italy", "Spain", "England", "Portugal", "Greece", "Peru", "Chile", "Brazil", "Argentina", "Bolivia", "Venezuela", "Australia", "New Zealand", "Fiji", "China", "India", "Thailand", "Afghanistan", "Bangladesh", "United States of America", "Canada", "Burundi", "Angola", "Kenya", "Togo")) %>%
  arrange(Country) %>%
  mutate(Country = factor(Country, Country))

# Matrix format
mat <- data
rownames(mat) <- mat[,1]
mat <- mat %>% dplyr::select(-Country, -Group, -Continent)
mat <- as.matrix(mat)

# Heatmap
#d3heatmap(mat, scale="column", dendrogram = "none", width="800px", height="80Opx", colors = "Blues")

library(heatmaply)
p <- heatmaply(mat, 
               dendrogram = "none",
               xlab = "", ylab = "", 
               main = "",
               scale = "column",
               margins = c(60,100,40,20),
               grid_color = "white",
               grid_width = 0.00001,
               titleX = FALSE,
               hide_colorbar = TRUE,
               branches_lwd = 0.1,
               label_names = c("Country", "Feature:", "Value"),
               fontsize_row = 5, fontsize_col = 5,
               labCol = colnames(mat),
               labRow = rownames(mat),
               heatmap_layers = theme(axis.line=element_blank())
)
p

p <- heatmaply(mat, 
               #dendrogram = "row",
               xlab = "", ylab = "", 
               main = "",
               scale = "column",
               margins = c(60,100,40,20),
               grid_color = "white",
               grid_width = 0.00001,
               titleX = FALSE,
               hide_colorbar = TRUE,
               branches_lwd = 0.1,
               label_names = c("Country", "Feature:", "Value"),
               fontsize_row = 5, fontsize_col = 5,
               labCol = colnames(mat),
               labRow = rownames(mat),
               heatmap_layers = theme(axis.line=element_blank())
)
p

##21 DIAGRAMA DE VENN
# Specific library
install.packages('UpSetR')
library(UpSetR)

# Dataset
input <- c(
  M.acuminata = 759,
  P.dactylifera = 769,
  A.thaliana = 1187,
  O.sativa = 1246,
  S.bicolor = 827,
  B.distachyon = 387,
  "P.dactylifera&M.acuminata" = 467,
  "O.sativa&M.acuminata" = 29,
  "A.thaliana&O.sativa" = 6,
  "S.bicolor&A.thaliana" = 9,
  "O.sativa&P.dactylifera" = 32,
  "S.bicolor&P.dactylifera" = 49,
  "S.bicolor&M.acuminata" = 49,
  "B.distachyon&O.sativa" = 547,
  "S.bicolor&O.sativa" = 1151,
  "B.distachyon&A.thaliana" = 10,
  "B.distachyon&M.acuminata" = 9,
  "B.distachyon&S.bicolor" = 402,
  "M.acuminata&A.thaliana" = 155,
  "A.thaliana&P.dactylifera" = 105,
  "B.distachyon&P.dactylifera" = 25,
  "S.bicolor&O.sativa&P.dactylifera" = 42,
  "B.distachyon&O.sativa&P.dactylifera" = 12,
  "S.bicolor&O.sativa&B.distachyon" = 2809,
  "B.distachyon&O.sativa&A.thaliana" = 18,
  "S.bicolor&O.sativa&A.thaliana" = 40,
  "S.bicolor&B.distachyon&A.thaliana" = 14,
  "O.sativa&B.distachyon&M.acuminata" = 28,
  "S.bicolor&B.distachyon&M.acuminata" = 13,
  "O.sativa&M.acuminata&P.dactylifera" = 35,
  "M.acuminata&S.bicolor&A.thaliana" = 21,
  "B.distachyon&M.acuminata&A.thaliana" = 7,
  "O.sativa&M.acuminata&A.thaliana" = 13,
  "M.acuminata&P.dactylifera&A.thaliana" = 206,
  "P.dactylifera&A.thaliana&S.bicolor" = 4,
  "O.sativa&A.thaliana&P.dactylifera" = 6,
  "S.bicolor&O.sativa&M.acuminata" = 64,
  "S.bicolor&M.acuminata&P.dactylifera" = 19,
  "B.distachyon&A.thaliana&P.dactylifera" = 3,
  "B.distachyon&M.acuminata&P.dactylifera" = 12,
  "B.distachyon&S.bicolor&P.dactylifera" = 23,
  "M.acuminata&B.distachyon&S.bicolor&A.thaliana" = 54,
  "P.dactylifera&S.bicolor&O.sativa&M.acuminata" = 62,
  "B.distachyon&O.sativa&M.acuminata&P.dactylifera" = 18,
  "S.bicolor&B.distachyon&O.sativa&A.thaliana" = 206,
  "B.distachyon&M.acuminata&O.sativa&A.thaliana" = 29,
  "O.sativa&M.acuminata&A.thaliana&S.bicolor" = 71,
  "M.acuminata&O.sativa&P.dactylifera&A.thaliana" = 28,
  "B.distachyon&M.acuminata&O.sativa&A.thaliana" = 7,
  "B.distachyon&S.bicolor&P.dactylifera&A.thaliana" = 11,
  "B.distachyon&O.sativa&P.dactylifera&A.thaliana" = 5,
  "A.thaliana&P.dactylifera&S.bicolor&O.sativa" = 21,
  "M.acuminata&S.bicolor&P.dactylifera&A.thaliana" = 23,
  "M.acuminata&B.distachyon&S.bicolor&P.dactylifera" = 24,
  "M.acuminata&O.sativa&S.bicolor&B.distachyon" = 368,
  "P.dactylifera&B.distachyon&S.bicolor&O.sativa" = 190,
  "P.dactylifera&B.distachyon&S.bicolor&O.sativa&A.thaliana" = 258,
  "P.dactylifera&M.acuminata&S.bicolor&B.distachyon&O.sativa" = 685,
  "M.acuminata&S.bicolor&B.distachyon&O.sativa&A.thaliana" = 1458,
  "S.bicolor&M.acuminata&P.dactylifera&O.sativa&A.thaliana" = 149,
  "B.distachyon&M.acuminata&P.dactylifera&O.sativa&A.thaliana" = 80,
  "M.acuminata&S.bicolor&B.distachyon&P.dactylifera&A.thaliana" = 113,
  "M.acuminata&S.bicolor&B.distachyon&P.dactylifera&O.sativa&A.thaliana" = 7674
)

# Plot
upset(fromExpression(input), nintersects = 40, nsets = 6, order.by = "freq", decreasing = T, mb.ratio = c(0.6, 0.4),
      number.angles = 0, text.scale = 1.1, point.size = 2.8, line.size = 1)

##22 Treemap
# libraries
library(tidyverse)
library(treemap)

# Load dataset from github
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/11_SevCatOneNumNestedOneObsPerGroup.csv", header=T, sep=";")
data[ which(data$value==-1),"value"] <- 1
colnames(data) <- c("Continent", "Region", "Country", "Pop")

# Plot
library(treemap)
p <- treemap(data,
             
             # data
             index=c("Continent", "Region", "Country"),
             vSize="Pop",
             type="index",
             
             # Main
             title="",
             palette="Dark2",
             
             # Borders:
             border.col=c("black", "grey", "grey"),             
             border.lwds=c(1,0.5,0.1),                         
             
             # Labels
             fontsize.labels=c(0.7, 0.4, 0.3),
             fontcolor.labels=c("white", "white", "black"),
             fontface.labels=1,            
             bg.labels=c("transparent"),              
             align.labels=list( c("center", "center"), c("left", "top"), c("right", "bottom")),                                  
             overlap.labels=0.5,
             inflate.labels=T   
             
)


##23 Dendogramas
# libraries
library(ggraph)
library(igraph)
library(tidyverse)
library(dendextend)
install.packages('colormap')
library(colormap)
library(kableExtra)
options(knitr.table.format = "html")

# create a data frame 
data=data.frame(
  level1="CEO",
  level2=c( rep("boss1",4), rep("boss2",4)),
  level3=paste0("mister_", letters[1:8])
)

# transform it to a edge list!
edges_level1_2 = data %>% select(level1, level2) %>% unique %>% rename(from=level1, to=level2)
edges_level2_3 = data %>% select(level2, level3) %>% unique %>% rename(from=level2, to=level3)
edge_list=rbind(edges_level1_2, edges_level2_3)

# Now we can plot that
mygraph <- graph_from_data_frame( edge_list )
ggraph(mygraph, layout = 'dendrogram', circular = FALSE) + 
  geom_edge_diagonal() +
  geom_node_point(color="#69b3a2", size=3) +
  geom_node_text(
    aes(  label=c("CEO", "Manager", "Manager", LETTERS[8:1]) ), 
    hjust=c(1,0.5, 0.5, rep(0,8)), 
    nudge_y = c(-.02, 0, 0, rep(.02,8)),
    nudge_x = c(0, .3, .3, rep(0,8))
  ) +
  theme_void() +
  coord_flip() +
  scale_y_reverse()

##Ahora armando clusters de datos
#Extraido de http://www.sthda.com/english/wiki/beautiful-dendrogram-visualizations-in-r-5-must-known-methods-unsupervised-machine-learning

# Load data
data(USArrests)
# Compute distances and hierarchical clustering
dd <- dist(scale(USArrests), method = "euclidean")
hc <- hclust(dd, method = "ward.D2")

# Put the labels at the same height: hang = -1
plot(hc, hang = -1, cex = 0.6)

# Convert hclust into a dendrogram and plot
hcd <- as.dendrogram(hc)

# Define nodePar
nodePar <- list(lab.cex = 0.6, pch = c(NA, 19), 
                cex = 0.7, col = "blue")
# Horizontal plot
plot(hcd,  xlab = "Height",
     nodePar = nodePar, horiz = TRUE)

# Triangle plot
plot(hcd,  xlab = "Height",type = "triangle",
     nodePar = nodePar, horiz = TRUE)

# Fan
install.packages("ape")
library("ape")
plot(as.phylo(hc), type = "fan")

# Cut the dendrogram into 4 clusters
colors = c("red", "blue", "green", "black")
clus4 = cutree(hc, 4)
plot(as.phylo(hc), type = "fan", tip.color = colors[clus4],
     label.offset = 1, cex = 0.7)

#mapa de calor con dendograma
install.packages('heatmaply')
library(tidyverse)
library(hrbrthemes)
library(viridis)
library(plotly)
#library(d3heatmap)

# Load data 
data <- read.table("https://raw.githubusercontent.com/holtzy/data_to_viz/master/Example_dataset/multivariate.csv", header=T, sep=";")
colnames(data) <- gsub("\\.", " ", colnames(data))

# Select a few country
data <- data %>% 
  filter(Country %in% c("France", "Sweden", "Italy", "Spain", "England", "Portugal", "Greece", "Peru", "Chile", "Brazil", "Argentina", "Bolivia", "Venezuela", "Australia", "New Zealand", "Fiji", "China", "India", "Thailand", "Afghanistan", "Bangladesh", "United States of America", "Canada", "Burundi", "Angola", "Kenya", "Togo")) %>%
  arrange(Country) %>%
  mutate(Country = factor(Country, Country))

# Matrix format
mat <- data
rownames(mat) <- mat[,1]
mat <- mat %>% dplyr::select(-Country, -Group, -Continent)
mat <- as.matrix(mat)

library(heatmaply)
p <- heatmaply(mat, 
               #dendrogram = "row",
               xlab = "", ylab = "", 
               main = "",
               scale = "column",
               margins = c(60,100,40,20),
               grid_color = "white",
               grid_width = 0.00001,
               titleX = FALSE,
               hide_colorbar = TRUE,
               branches_lwd = 0.1,
               label_names = c("Country", "Feature:", "Value"),
               fontsize_row = 5, fontsize_col = 5,
               labCol = colnames(mat),
               labRow = rownames(mat),
               heatmap_layers = theme(axis.line=element_blank())
)
p